[go: up one dir, main page]

Menu

[r3]: / HOWTOUSE  Maximize  Restore  History

Download this file

62 lines (45 with data), 2.5 kB

How to use vosm to 
a) train a face model 
b) fit an untrained face using the trained face model

First of all, in order to use vosm, you need to find and download 
respective ShapeInfo.txt files summarized in the table at 
http://www.visionopen.com/cv/2dsm.php

Secondly, you have to find and download or buy the standard
annotated face databases by yourself.

Help on two commands "vo_smbuilding" and "vo_smfitting".
./vo_smbuilding --help
Usage: vo_smbuilding [options] save_directory annotation_directory image_directory shapeinfo_path database channels type levels percentage 
options: 
   -o   output directory (default './') 
   -a   annotation directory (required) 
   -i   image directory (required) 
   -s   path of the file shapeinfo (required, please find and download the corresponding ShapeInfo.txt files from 
		my website http://www.visionopen.com/cv/2dsm.php)
   -d   training database (required) 
   -c   channels (1 or 3, default 3) 
   -t   statistical model type (SM, TM, AM, IA, FM, SMLTC, SMNDPROFILE. default SMNDPROFILE ) 
   -l   level of parymid (default 4) 
   -p   percentage of shape, texture and appearance PCA (default 0.95) 
Note: If you are building SMLTC or SMNDPROFILE, you must specify 
 -c 1, namely, SMLTC and SMNDPROFILE can only deal with gray-level images. 


./vo_smfitting --help
Usage: vo_smfitting [options] trained_data type testing_images testing_annotations  
options: 
   -o   trained data directory (required)
   -t   fitting method to be used (ASM_PROFILEND, ASM_LTC, AAM_BASIC, AAM_CMUICIA, AAM_IAIA. default ASM_PROFILEND ) 
   -i   testing image directory containing at least one image (required)
   -a   testing annotation directory (can be ignored) 
   -d   testing database -- if annotation directory is specified, database should also be specified for further evaluation on fitting performance (can be ignored) 
   -s   static image sequence or dynamic image sequence (default value true) 
   -r   recording the fitting results or not (default value false) 




Tow examples are given as:

vo_smbuilding -a "/media/usb0/Research/Databases/face/2D/emount/annotations/training" 
-i "/media/usb0/Research/Databases/face/2D/emount/images/training" 
-s "/media/usb0/Research/Databases/face/2D/emount/annotations/training/ShapeInfo.txt" 
-d "EMOUNT"
-t "SM"


vo_smfitting -o "/media/usb0/Research/Databases/face/2D/BIOID/traineddata/397Frontal/Gray" 
-t "ASM_PROFILEND" 
-i "/media/usb0/Research/Databases/face/2D/BIOID/images/testing" 
-s "true" 
-r "true"